How Alpha Zero used Reinforcement Learning to Master Chess (12.5)
End to End machine learning is one of the dreams of deep learning. This would allow machine learning to process data with limited preprocessing and learn with minimal human knowledge. AlphaZero was able to master chess in 40 hours simply by playing itself. No prior human chess knowledge was used. This video provides an overview of AlphaZero and some of the technologies used by it that were covered in this course.
Code for This Video:
https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class_12_05_alpha_zero.ipynb
Course Homepage: https://sites.wustl.edu/jeffheaton/t81-558/
Follow Me/Subscribe:
https://www.youtube.com/user/HeatonResearch
https://github.com/jeffheaton
Tweets by jeffheaton
Support Me on Patreon: https://www.patreon.com/jeffheaton